Yeritza Gómez of INAOE

The growing adoption of the Internet of Medical Things (IoMT) has improved healthcare through real-time data exchange and device interconnectivity. However, this rapid adoption also increases the attack surface, exposing critical systems to cyber threats. Current intrusion detection systems (IDS) are typically centralized and computationally intensive, making them unsuitable for resource-constrained IoMT environments. This research proposes a hierarchical and modular detection framework that distributes anomaly detection to the network edge while delegating classification tasks to cloud-based models, enabling early threat identification without compromising network performance by leveraging edge interactions.

Biography:

A biomedical engineer who graduated from the National Polytechnic Institute (IPN) in Mexico, where she completed a research project analyzing physiological signals during the use of N95 face masks and under various exercise conditions. She has collaborated on neuroengineering instrumentation and physiological signal processing projects with various universities in Mexico. Professionally, she has worked in medical equipment maintenance and procurement and in the education sector as a teacher for students at various levels in both the public and private sectors.
She is currently pursuing a Master’s degree in Computational Sciences at the National Institute of Astrophysics, Optics, and Electronics (INAOE) in the Cybersecurity Laboratory, focusing on the identification of attacks using machine learning in Medical Internet of Things (IoMT) ecosystems.

Email:

Address:San Andrés Cholula, Puebla, Mexico, 72480